@inproceedings{song-etal-2022-speak,
title = "Speak: A Toolkit Using {A}mazon {M}echanical {T}urk to Collect and Validate Speech Audio Recordings",
author = "Song, Christopher and
Harwath, David and
Alhanai, Tuka and
Glass, James",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.787",
pages = "7253--7258",
abstract = "We present Speak, a toolkit that allows researchers to crowdsource speech audio recordings using Amazon Mechanical Turk (MTurk). Speak allows MTurk workers to submit speech recordings in response to a task prompt and stimulus (e.g. image, text excerpt, audio file) defined by researchers, a functionality that is not natively offered by MTurk at the time of writing this paper. Importantly, the toolkit employs numerous measures to ensure that speech recordings collected are of adequate quality, in order to avoid accepting unusable data and prevent abuse/fraud. Speak has demonstrated utility, having collected over 600,000 recordings to date. The toolkit is open-source and available for download.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="song-etal-2022-speak">
<titleInfo>
<title>Speak: A Toolkit Using Amazon Mechanical Turk to Collect and Validate Speech Audio Recordings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Harwath</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tuka</namePart>
<namePart type="family">Alhanai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Glass</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present Speak, a toolkit that allows researchers to crowdsource speech audio recordings using Amazon Mechanical Turk (MTurk). Speak allows MTurk workers to submit speech recordings in response to a task prompt and stimulus (e.g. image, text excerpt, audio file) defined by researchers, a functionality that is not natively offered by MTurk at the time of writing this paper. Importantly, the toolkit employs numerous measures to ensure that speech recordings collected are of adequate quality, in order to avoid accepting unusable data and prevent abuse/fraud. Speak has demonstrated utility, having collected over 600,000 recordings to date. The toolkit is open-source and available for download.</abstract>
<identifier type="citekey">song-etal-2022-speak</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.787</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>7253</start>
<end>7258</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Speak: A Toolkit Using Amazon Mechanical Turk to Collect and Validate Speech Audio Recordings
%A Song, Christopher
%A Harwath, David
%A Alhanai, Tuka
%A Glass, James
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F song-etal-2022-speak
%X We present Speak, a toolkit that allows researchers to crowdsource speech audio recordings using Amazon Mechanical Turk (MTurk). Speak allows MTurk workers to submit speech recordings in response to a task prompt and stimulus (e.g. image, text excerpt, audio file) defined by researchers, a functionality that is not natively offered by MTurk at the time of writing this paper. Importantly, the toolkit employs numerous measures to ensure that speech recordings collected are of adequate quality, in order to avoid accepting unusable data and prevent abuse/fraud. Speak has demonstrated utility, having collected over 600,000 recordings to date. The toolkit is open-source and available for download.
%U https://aclanthology.org/2022.lrec-1.787
%P 7253-7258
Markdown (Informal)
[Speak: A Toolkit Using Amazon Mechanical Turk to Collect and Validate Speech Audio Recordings](https://aclanthology.org/2022.lrec-1.787) (Song et al., LREC 2022)
ACL